Human evidence verification method, device, electronic device and storage medium

Abstract

The present invention discloses a method, device, electronic device, and storage medium for human identity verification. After collecting the identity document information of a target verification person, it is determined whether there is a candidate face image in the list of faces to be verified; wherein, the candidate face image is obtained from the verification scene image before the verification of the target verification person; if it exists, human identity verification is performed based on the candidate face image and the identity document information of the target verification person, and at the same time, the current verification scene image is collected to update the list of faces to be verified. This technical solution does not require additional costs and improves the passing efficiency of human identity verification devices.

Description

Technical Field

[0001] The present invention relates to the technical field of face recognition, and in particular, to a method, device, electronic device, and storage medium for verifying the identity of a person and a certificate. Background Art

[0002] Nowadays, identity verification is carried out on the people entering entrances such as railway stations and airports to ensure the accuracy and traceability of the identities of the people. Currently, identity verification devices are generally used to replace manual verification, thereby reducing the consumption of manpower and improving the passing efficiency.

[0003] Currently, in the prior art, every time a person passes through, the verification device separately collects the photo and identity document information of the verified person to verify the identity of the person. However, when there are many people queuing, since the identity verification device needs to separately collect the face and identity document of each person each time, and compare and verify the currently collected face data with the identity document, the passing efficiency is not high, and queuing congestion is likely to occur. Summary of the Invention

[0004] The present invention provides a method, device, electronic device, and storage medium for verifying the identity of a person and a certificate, so as to solve the congestion problem caused by a large number of people queuing at the entrance during identity verification of a person and a certificate, and achieve high-efficiency passing.

[0005] According to one aspect of the present invention, a method for verifying the identity of a person and a certificate is provided, including:[[]]

[0006] After collecting the certificate information of the target verified person, determining whether there is a candidate face image in the list of faces to be verified; wherein, the candidate face image is obtained from the verification scene image before the target verified person is verified;

[0007] If there is, performing identity verification of the person and the certificate according to the candidate face image and the certificate information of the target verified person, and at the same time collecting the current verification scene image to update the list of faces to be verified.

[0008] According to another aspect of the present invention, a device for verifying the identity of a person and a certificate is provided, including:[[]]

[0009] An image recognition module, after collecting the certificate information of the target verified person, determining whether there is a candidate face image in the list of faces to be verified; wherein, the candidate face image is obtained from the verification scene image before the target verified person is verified;

[0010] An operation module, if there is, performing identity verification of the person and the certificate according to the candidate face image and the certificate information of the target verified person, and at the same time collecting the current verification scene image to update the list of faces to be verified.

[0011] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0012] at least one processor; and

[0013] a memory communicatively connected to the at least one processor; wherein,

[0014] the memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the identity verification method according to any embodiment of the present invention.

[0015] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for implementing the identity verification method according to any embodiment of the present invention when executed by a processor.

[0016] In the technical solution of the embodiment of the present invention, when performing identity verification on a target verification person, after collecting the document information of the target verification person, it is determined whether there is a candidate face image in the list of faces to be verified, and the candidate face image can be obtained from the verification scene image when the previous historical verification person verified by the target verification person; if there is a candidate face image in the list of faces to be verified, identity verification is performed based on the candidate face image and the document information of the target verification person, and at the same time, the current verification scene image is collected to update the list of faces to be verified, solving the congestion problem caused by a large number of people queuing at the entrance during identity verification and improving the passing efficiency of the identity verification device.

[0017] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 is a flowchart of an identity verification method according to Embodiment 1 of the present invention;

[0020] Figure 2 is a scene diagram for implementing the identity verification of the embodiment of the present invention;

[0021] Figure 3It is a flowchart of a human identity verification method provided in Embodiment 2 of the present invention;

[0022] Figure 4 It is a schematic structural diagram of a human identity verification device provided in Embodiment 4 of the present invention;

[0023] Figure 5 It is a schematic structural diagram of an electronic device for implementing the human identity verification method of the embodiments of the present invention. Detailed implementation manners

[0024] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0025] It should be noted that the terms "first", "second", "target", "candidate", etc. in the specification and claims of the present invention and the above drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0026] Embodiment 1

[0027] Figure 1 As a flowchart of a human identity verification method provided in Embodiment 1 of the present invention, this embodiment is applicable to the situation of human identity verification. This method can be executed by a human identity verification device, which can be implemented in the form of hardware and / or software, and the human identity verification device can be configured in a human identity verification device. As Figure 1 shown, this method includes:

[0028] S110. After collecting the certificate information of the target verification person, determine whether there is a candidate face image in the list of faces to be verified; wherein, the candidate face image is obtained from the verification scene image before the target verification person is verified.

[0029] The present invention is applicable to the scenario of human identity verification. For example, due to the installation position of the verification device, there will be a field of view angle between the queuing personnel and the verification device. And according to the planning of the queuing channels at the entrances and exits of railway stations, airports, etc., people in the queuing channels can automatically adjust the queuing line. Therefore, when the current verification personnel are performing identity verification, the camera module of the human identity verification device can simultaneously collect the face information of other personnel behind the current verification personnel in the queue.

[0030] Among them, the target verification personnel are the personnel currently being verified on the verification device, which can be understood as the person closest to the verification device in the verification queue, that is, the first person in the verification queue. The list of faces to be verified can be a list of face images that meet the verification criteria in the verification queue collected simultaneously during human identity verification, sorted in ascending order according to the distance between the face and the verification device from small to large; there cannot be two or more face images with a similarity greater than a preset threshold in the list of faces to be verified. Among them, the verification criteria are used to ensure the accuracy of the comparison result of the faces in the face images, and can be specifically determined according to whether the facial features are complete, the angle is appropriate, and the face size meets the threshold requirements, etc. The specific appropriate angle range and face size range can be adjusted according to the actual face recognition algorithm. The distance relationship between the face and the verification device can be determined according to the size of a normal face or the distance between a person's two eyes. Exemplarily, when the verification device is a binocular camera, the position information can be directly determined according to the image obtained by the camera, and then the distance information between the face and the verification device can be determined in combination with the size of the face in the image and the distance between the two eyes of the person. When the distance between a certain face and the verification device in the obtained image exceeds a certain threshold, the face image is not collected to ensure the quality of the candidate face images in the list of faces to be verified.

[0031] The candidate face images are obtained from the verification scenario images when the historical verification personnel before the target verification personnel are verified. The candidate face images can be at least one face image existing in the list of faces to be verified. The historical verification personnel are the personnel who have completed human identity verification on the human identity verification device. Specifically, when the historical verification personnel are verified, face extraction is performed on the images collected during verification. If there are other face images in addition to the historical verification personnel, and the face image meets the verification criteria, indicating that the person corresponding to the face image is in the queue where the historical verification personnel are located, then the face image is added to the list of faces to be verified so that the person corresponding to the face image can be directly compared during human identity verification. Such as Figure 2Scene diagram of human identity verification. In front of the verification device, the queue members are arranged in the order of A, B, and C. When person A is undergoing human identity verification, the image captured by the image acquisition module of the verification device includes both the face image of A and the face image of B. Then, the face image of B is added to the list of faces to be verified. When A has completed the verification and becomes a historical verified person, B becomes the target verification person, that is, the first person in the queue. After the ID information of B is collected, the ID information of B is directly compared with the candidate face images in the list of faces to be verified, without the need to capture the face image of B again, saving time.

[0032] S120. If there is one, perform human identity verification based on the candidate face image and the ID information of the target verification person, and at the same time capture the current verification scene image to update the list of faces to be verified.

[0033] Specifically, the verification device is usually deployed in places such as entrances and exits where the identity of personnel needs to be verified. After the ID module in the verification device collects the ID information, the image acquisition module will start to capture the current verification scene image to obtain the face image of the current verification person. Among them, the ID module can specifically be: an OCR (Optical Character Recognition) recognition device or an RFID (Radio Frequency Identification) chip recognition device; the image acquisition module can specifically be: a camera or a video camera, such as a monocular camera or a binocular video camera, etc. In the embodiments of the present invention, there are no specific limitations on the ID module and the image acquisition module. After the verification device collects the ID information of the target verification person, if there are candidate face images in the list of faces to be verified, it means that the historical verified person captured the face images of the people behind the queue during the verification. Then, perform human identity verification based on the candidate face images and the ID information of the target verification person, and at the same time, the image acquisition module of the verification device is activated to capture the current verification scene image to update the list of faces to be verified according to the current verification scene image. On the one hand, capturing the current verification scene image can capture the faces of the people behind the current verification person to update the list of faces to be verified, ensuring that subsequent personnel can directly obtain the images from the list of faces to be verified when undergoing human identity verification. On the other hand, if the human identity verification of the current verification person fails according to the list of faces to be verified, the face image can be directly obtained from the current verification scene, ensuring the efficiency and success rate of the verification.

[0034] In a feasible embodiment, the list of faces to be verified includes at least two candidate face images, and the at least two candidate face images are sorted according to the distance between the face and the verification device;

[0035] Correspondingly, performing identity verification based on the candidate face image and the identification information of the target verification personnel includes:

[0036] Performing identity verification on the candidate face images and the identification information of the target verification personnel in sequence according to the sorting result;

[0037] If the identity verification is successful, deleting the verified candidate face images in the to-be-verified face list;

[0038] If the identity verification fails, deleting all candidate face images in the to-be-verified face list, and performing re-verification according to the updated to-be-verified face list.

[0039] Specifically, if at least two images of non-historical verification personnel are collected during the identity verification of historical verification personnel, sorting them in ascending order according to the distance between the face and the verification device, and adding the face images to the to-be-verified face list. The distance between the face and the verification device can be determined according to the position information of the face in the image, the size of the face, and the distance between the eyes.

[0040] Exemplarily, referring to Table 1 as the to-be-verified face list, the face images in the to-be-verified face list are arranged in sequence as P1, P2, and P3. When target verification personnel A performs identity verification, images of the current verification scene are collected simultaneously. Comparing the identification information of A with P1 in the to-be-verified face list, if the verification is successful, deleting P1; if the identity verification is unsuccessful, continue to verify with P2 in the to-be-verified face list.

[0041] If the identity verification is successful, deleting P1 and P2; if the identity verification fails,

[0042] Continue to verify with P3 in the to-be-verified face list. If the identity verification is successful, deleting P1, P2, and P3; if the identity verification fails, deleting P1, P2, and P3, and performing re-verification according to the to-be-verified face list updated with the images of the current verification scene. The to-be-verified face list updated with the images of the current verification scene includes the face images of the current verification personnel.

[0043] Table 1

[0044] Face ID Current verification order Face A P1 Face B P2 Face C P3

[0045] In this technical solution, based on at least two candidate face images in the face list to be verified that are sorted in ascending order according to the distance between the face and the verification device, a person-certificate verification is performed with the certificate information of the target verification person. If the person-certificate verification is successful, the verified candidate face images in the face list to be verified are deleted. If the person-certificate verification fails, all candidate face images in the face list to be verified are deleted, and a re-verification is performed based on the updated face list to be verified until the person-certificate verification is successful. When verifying the target verification person, the comparison is preferentially made with the face images in the face list to be verified, which improves the verification efficiency; and when the comparison is successful, all face data before the successful comparison in the face list to be verified are deleted to ensure the reliability of the data in the face list to be verified.

[0046] In a feasible embodiment, collecting the current verification scene image to update the face list to be verified includes:

[0047] Extracting face images from the current verification scene image to obtain the current face images, and sorting the current face images in ascending order according to the distance between the face and the verification device;

[0048] If it is determined that the person-certificate verification of the target verification person is successful, after deleting the face image ranked first in the current face images, the face list to be verified is updated;

[0049] If it is determined that the person-certificate verification of the target verification person fails, the face list to be verified is updated according to whether the face image ranked first in the current face images meets the verification standard, and the person-certificate verification of the target verification person is performed according to the updated face list to be verified. Specifically, when the person-certificate verification of the target verification person is being performed, the current verification scene image will be collected simultaneously. By determining the facial contour of the collected face image according to the verification standard, and obtaining the distance information between the collected face and the person-certificate verification device based on the position information of the face in the image, the size of the face, and the distance between the eyes. After extracting the face images from the current verification scene image, the current face images are sorted in ascending order according to the distance between the face and the verification device. If the person-certificate verification of the target verification person is successful, since the face image ranked first in the current face images is the target verification person, after deleting the face image ranked first in the current face images, the remaining collected face images are added to the face list to be verified; if the person-certificate verification of the target verification person fails and the target verification person needs to be re-collected for images, the face list to be verified is updated according to whether the face image ranked first in the current face images meets the verification standard. Only when the face image ranked first in the current face images meets the verification standard can the success rate of the person-certificate verification result of the target verification person be ensured, and then the person-certificate verification of the target verification person is performed according to the updated face list to be verified until the person-certificate verification is successful.

[0050] Exemplarily, before the verification device, three verification personnel A, B, and C are arranged in sequence. When the target verification personnel A conducts the identity verification, the image of the current verification scenario will be collected simultaneously, that is, the face images of A, B, and C that meet the verification standards are collected, and the face images of A, B, and C are sorted in ascending order according to the distance between the face and the verification device, that is, sorted as A1, B1, and C1. The face image A1 ranked first is defaulted to be the face image of A. When the identity verification of A is successful, the face image A1 in the sorted A1, B1, and C1 is deleted, and the list of faces to be verified is updated according to the image of the current verification scenario. When the identity verification of A fails respectively with A1, B1, and C1, the list of faces to be verified is updated according to whether the face image closest to the device in the current face images of the current verification scenario meets the verification standards. The identity verification of the target verification personnel A is carried out according to the updated list of faces to be verified until the identity verification is successful.

[0051] In this technical solution, the face images of the current verification scenario are collected, and the current face images are sorted in ascending order according to the distance between the face and the verification device. After the identity verification is successful, after deleting the face image ranked first in the current face images, the list of faces to be verified is updated, ensuring the accuracy of the data in the list of faces to be verified. In addition, the face collection of the current target verification personnel is advanced to the time when the previous target verification personnel is verified. This can not only increase the collection time and frequency, but also advance the screening of the collected face images to the previous target verification personnel. When the current target personnel is verified, only face comparison is required, without face feature extraction, which can also improve the comparison efficiency and shorten the passing time.

[0052] In a feasible embodiment, updating the list of faces to be verified according to whether the face image ranked first in the current face images meets the verification standards includes:

[0053] If it meets the verification standards, the current face images are stored in the list of faces to be verified according to the distance between the face and the verification device, and the target verification personnel are verified according to the updated list of faces to be verified;

[0054] If it does not meet the verification standards, the image of the current verification scenario is collected again until it is determined that the face image ranked first meets the verification standards, and the list of faces to be verified is updated according to all the collected images of the current verification scenario.

[0055] Specifically, only when the face image ranked first in the current face images meets the verification standards can the correctness of the result of the identity verification of the target verification personnel be ensured.

[0056] For example, after the current face images are sorted in ascending order by distance, the results are A1, A2, and A3. A1 is the closest to the verification device and is considered the target verification person undergoing verification. Check whether A1 meets the verification standard. If A1 meets the verification standard, store the current face images in the face list to be verified according to the distance between the face and the verification device, that is, store A1, A2, and A3 in the face list to be verified in sequence, and verify the target verification person based on the updated face list to be verified. That is to say, compare the ID information of the target verification person with A1. If A1 does not meet the verification standard, re-collect the current verification scene image until it is determined that A1 meets the verification standard, and update the face list to be verified based on all the face images collected during this process.

[0057] In this technical solution, by determining whether the face image ranked first in the current face images meets the verification standard, the collected face images can be more accurate, enabling comparison based on the updated face list to be verified after the initial comparison between the target verification person and the face list to be verified fails, effectively reducing the number of times of re-collecting images during the ID verification of the target verification person and improving the efficiency of successful ID verification.

[0058] In a feasible embodiment, updating the face list to be verified according to all the currently collected verification scene images includes:

[0059] After each current verification scene image is collected, compare the face images ranked non-first in the current face images with the candidate face images in the face list to be verified. If there is a face image with a similarity greater than the preset threshold, select the face image with the maximum image quality score among the face images with a similarity greater than the preset threshold and store it in the face list to be verified according to the distance between the face and the verification device;

[0060] After the face image ranked first that meets the verification standard is collected, store the face image ranked first in the face list to be verified.

[0061] Specifically, after multiple current verification scenario images are collected, it will result in duplicates of the extracted face images. Therefore, it is necessary to screen the duplicate face images according to the image quality score to ensure the uniqueness of the candidate face images in the face list to be verified. Among them, the image quality score is determined according to the clarity of the image, as well as the size and angle of the face in the image. Exemplarily, if there are two face images with a similarity greater than a preset threshold, the image with higher clarity is selected as the screened image, or when the clarity difference between the images is less than a preset range, the image with a larger face is selected as the screened image. In the embodiments of the present invention, the specific evaluation criteria for the image quality score are not limited, and screening according to the image quality score ensures that the screened image is more easily recognizable.

[0062] Exemplarily, if there are face images C' and D' of two persons C and D in the current face list to be verified, and there are four persons A, B, C, and D to be verified in sequence in the current verification scenario image, the face images of A, B, C, and D are collected and sorted in ascending order according to the distance between the face and the verification device to obtain face images A1, B1, C1, and D1. Then, B1, C1, and D1 are compared with C' and D'. It is found that the similarity between C1 and C' is greater than the preset threshold and the quality score of C1 is higher, and the similarity between D1 and D' is greater than the preset threshold and the quality score of D' is higher. Then, C1 and D' are stored in the face list to be verified, and C' and D1 are deleted. At this time, the face list to be verified is B1, C1, and D'. If A1 meets the verification standard, it is stored in the face list to be verified, and the face list to be verified is A1, B1, C1, and D'; if A1 does not meet the verification standard, the current verification scenario image is collected again. At this time, the collected face images are sorted in ascending order according to the distance between the face and the verification device as A11, B11, C11, and D11. B11, C11, and D11 are compared with B1, C1, and D' stored in the face list to be verified last time. If there are face images with a similarity greater than the preset threshold, only one face image with the maximum quality score is retained in the face list to be verified, and the rest are deleted. That is, if the similarity between B11 and B1 is greater than the preset threshold and the quality score of B1 is higher, then B1 is retained and B11 is deleted. The remaining face images are compared and screened in the same way. At this time, if A11 meets the verification standard, it is stored in the face list to be verified. If A11 does not meet the verification standard, the current verification scenario image is collected again, and the process is carried out according to the above screening order until the first face image that meets the verification standard is selected and stored in the face list to be verified.

[0063] According to all the currently collected verification scene images, the face list to be verified is updated. After collecting the current verification scene images, before storing the face images that are not ranked first in the current face images, by comparing the similarity with the candidate face images in the face list to be verified, only one face image with the maximum quality score among the multiple face images with a similarity greater than the preset threshold is retained and stored in the face list to be verified, ensuring the accuracy of the images in the face list to be verified, avoiding duplicate list information caused by multiple collections, and improving the accuracy of human identity verification.

[0064] In a feasible embodiment, after deleting the face image ranked first in the current face images, updating the face list to be verified includes:

[0065] Compare the face images that are not ranked first in the current face images with the candidate face images in the face list to be verified. If there are face images with a similarity greater than the preset threshold, screen the face images with a similarity greater than the preset threshold according to the image quality score, and select the face image with the maximum image quality score among them;

[0066] Store the screened current face images in the face list to be verified according to the distance between the face and the verification device.

[0067] Specifically, if it is determined that the human identity verification of the target verification person is successful, delete the face image ranked first in the current face images, and compare the face images that are not ranked first in the current face images with the candidate face images in the face list to be verified. If there are face images with a similarity greater than the preset threshold, it indicates duplicate collection of face images. Screen the face images with a similarity greater than the preset threshold according to the image quality score, select the face image with the maximum image quality score among them, and store the screened face images in the face list to be verified according to the distance between the face and the verification device to form a new face list to be verified.

[0068] According to this technical solution, by comparing and screening the current face images with the face list to be verified according to the similarity preset threshold and the image quality score, eliminating the redundant face images with a similarity greater than the preset threshold, and then updating the face list to be verified with the current face images according to the distance between the face and the verification device, the face list to be verified can be updated in a timely manner, ensuring the accuracy of the face list to be verified and improving the comparison efficiency of human identity verification.

[0069] In the technical solution of the embodiment of the present invention, when the target verification personnel perform identity verification, after collecting the ID information of the target verification personnel, it is determined whether there is a candidate face image in the list of faces to be verified. The candidate face image can be obtained from the verification scene image during the verification of the historical verification personnel before the target verification personnel's verification; when there is a candidate face image in the list of faces to be verified, identity verification is performed based on the candidate face image and the ID information of the target verification personnel, and at the same time, the current verification scene image is collected to update the list of faces to be verified, solving the congestion problem caused by the large number of people queuing at the entrance during identity verification and improving the passing efficiency of the identity verification device.

[0070] Embodiment 2

[0071] Figure 3 It is a flowchart of an identity verification method provided according to Embodiment 2 of the present invention. This method describes the situation where there is no candidate face image in the list of faces to be verified based on the embodiment of this solution. As Figure 3 shown, the method includes:

[0072] S210. After collecting the ID information of the target verification personnel, determine whether there is a candidate face image in the list of faces to be verified; wherein, the candidate face image is obtained from the verification scene image before the verification of the target verification personnel.

[0073] S220. If not, collect the current verification scene image, extract the face image from the current verification scene image to obtain the current face image; sort the current face images in ascending order according to the distance between the face and the verification device; update the list of faces to be verified according to whether the face image ranked first in the current face images meets the verification standard, and perform identity verification on the target verification personnel according to the updated list of faces to be verified.

[0074] Specifically, after collecting the ID information of the target verification personnel, if it is found that there is no candidate face image in the list of faces to be verified, it means that the face images of the subsequent teams were not collected during the verification by the historical verification personnel. For example, due to angle deviation, the historical verification personnel only collected the face image of the first person in the current team during verification. Then, the current verification scene image is collected, and the face images in the current verification scene image are extracted. The list of faces to be verified is updated according to whether the face image ranked first in the current face images meets the verification standard. If it meets the verification standard, the current face image is stored in the list of faces to be verified according to the distance between the face and the verification device, and the target verification personnel are verified according to the updated list of faces to be verified. If it does not meet the verification standard, the current verification scene image is collected again. Before storing the face images ranked non-first in the current face images, a similarity comparison is made with the candidate face images in the list of faces to be verified. If there is a face image with a similarity greater than the preset threshold, the face image with the maximum image quality score among the face images with a similarity greater than the preset threshold is selected, and the other face images with a similarity greater than the preset threshold are deleted until it is determined that the face image ranked first meets the verification standard, and the list of faces to be verified is updated according to all the currently collected verification scene images.

[0075] For example, when target verification personnel A conducts identity verification and finds that there is no candidate face image in the list of faces to be verified, it is necessary to collect images of the current verification scene. At this time, the face images of A and B are collected and sorted in ascending order of the distance between the face and the verification device as A1 and B1. B1 is directly stored in the list of faces to be verified. If A1 meets the verification standard, A1 is stored in the list of faces to be verified, and then the identity verification of target verification personnel A is performed according to the updated list of faces to be verified A1 and B1. If A1 does not meet the verification standard, it is necessary to collect the current verification scene image again, and the obtained face images are sorted in ascending order of the distance between the face and the verification device as A11 and B11. Before storing B11 in the list of verified faces, it is judged whether the similarity between B11 and B1 is greater than the preset threshold. If the similarity between B11 and B1 is greater than the preset threshold and the image quality score of B1 is higher, then B11 is deleted. If the similarity between B11 and B1 is less than the preset threshold, then B11 is directly stored in the list of verified faces. It is judged whether A11 meets the verification standard. If it meets the standard, the identity verification is performed according to the updated list of faces to be verified. If it does not meet the standard, the above process of collecting the current verification scene image again and updating the list of faces to be verified is continued until the face image ranked first meets the verification standard, and then the identity verification is performed according to the updated list of faces to be verified.

[0076] In this technical solution, when it is determined that there is no candidate face image in the face list to be verified, the face image of the current verification scene is collected, and the current face images are sorted in ascending order according to the distance between the face and the verification device. Then, according to whether the face image ranked first in the current face images meets the verification standard, the face list to be verified is updated, and the target verification personnel are verified based on the updated face list to be verified, so as to quickly and accurately update the candidate face images in the face list to be verified, so as to improve the verification efficiency when subsequent verification personnel conduct verification.

[0077] Embodiment III

[0078] This embodiment provides a feasible implementation manner of the method for verifying identity documents with face, which is as follows:

[0079] In this embodiment, after the identity document information of the target verification personnel is collected, it is determined whether there is a candidate face image in the face list to be verified; among them, the candidate face image is obtained from the verification scene images during the verification of historical verification personnel before the target verification personnel are verified. If it exists, identity document verification is performed based on the candidate face image and the identity document information of the target verification personnel, and at the same time, the current verification scene image is collected to update the face list to be verified. If it does not exist, the current verification scene image is collected, face images are extracted from the current verification scene image to obtain the current face images; the current face images are sorted in ascending order according to the distance between the face and the verification device; according to whether the face image ranked first in the current face images meets the verification standard, the face list to be verified is updated, and the target verification personnel are verified based on the updated face list to be verified.

[0080] For example, currently, there are verification personnel arranged in sequence as A, B, and C, and all of A, B, and C can collect face images that meet the verification standard. The verification device collects images of the current verification scene. According to the normal face size or the size of the distance between the two eyes of a person, the distance relationship between the verification personnel and the verification device can be obtained, and the collected face images are sorted in ascending order of the distance between the face and the verification device as P1, P2, and P3, and stored in the face list to be verified.

[0081] When person A undergoes identity verification, the verification device will simultaneously collect the information of the target verification person A and the images of the current verification scene. The information of the target verification person A is first compared with the face image of P1 in the list of faces to be verified. If the comparison with P1 is unsuccessful, it will be compared with P2, and so on. If all comparisons are unsuccessful, the images of the current verification scene will be collected again, and at the same time, all the images in the list of faces to be verified will be cleared. If the comparison with P1 is successful, the target verification person A will pass the verification, and the face image of P1 in the list of faces to be verified will be deleted. At the same time, the order in the original list of faces to be verified will be advanced. For example, the original P2 becomes P1, and so on. At this time, the list of faces to be verified is P1 and P2.

[0082] The verification person A has passed the verification. The verification person B becomes the target verification person and undergoes identity verification. At this time, only the identity information of the target verification person B needs to be collected to immediately conduct the verification comparison, that is, to compare with P1 (i.e., P2 when the original target verification person A was verified) in the list of faces to be verified, without waiting for the result of the face image collection of the target verification person B again.

[0083] When currently collecting the identity information of the target verification person B, the verification device will also normally collect face images (assuming that the faces that meet the verification standards collected at this time are P1' and P2' respectively, and the verified persons collected are stored in the list of faces to be verified according to the distance between the face and the verification device). At this time, no verification standard judgment is made on the face with the closest distance collected, and P1 in the list of faces to be verified can be directly used for comparison. It is equivalent to collecting the face images of the target verification person B in advance, thereby improving the verification efficiency. At this time, the list of faces to be verified is P1, P2, P1', and P2'.

[0084] When the target verification person B passes the identity verification, P1 in the list of faces to be verified will be deleted (if the comparison with P2 in the list of persons to be verified is successful when the target verification person B is verified, then P2 and all the faces in the list of faces to be verified before P2 will be deleted. At this time, it is considered that the previous candidate faces have completed the verification and the corresponding face images are invalid), and at the same time, the face P1' with the closest distance collected when the target verification person B is verified will also be deleted (since the target verification person B passes the verification, it is considered that P1' is the face image of the current target verification person B and is directly deleted).

[0085] In this technical solution, when verifying the identity of the target verification person, it first compares with the candidate face images in the list of faces to be verified that have been collected currently, rather than waiting for the current acquisition result of the face image of the target verification person every time. Therefore, it can perform the comparison immediately when the identity document information of the target verification person is collected, improving the verification efficiency and shortening the passage time. At the same time, the face collection of the current target verification person is advanced to the time when the previous target verification person is being verified. This can not only increase the collection time and frequency, improve the image quality of the candidate face images in the list of faces to be verified during multiple collections, and thus improve the verification success rate, but also advance the screening of the collected face images to the previous target verification person, and update the list of faces to be verified in a timely manner to ensure the reliability of the candidate face images in the list of faces to be verified.

[0086] Embodiment 4

[0087] Figure 4 FIG. is a schematic structural diagram of a human identity verification device according to Embodiment 4 of the present invention. As Figure 4 shown, the device includes:

[0088] An image recognition module 310, configured to determine whether there are candidate face images in the list of faces to be verified after collecting the identity document information of the target verification person; wherein, the candidate face images are obtained from the verification scene images before the target verification person is verified;

[0089] An operation module 320, configured to, if any, perform human identity verification based on the candidate face images and the identity document information of the target verification person, and at the same time collect the current verification scene image to update the list of faces to be verified.

[0090] Optionally, the list of faces to be verified includes at least two candidate face images, and the at least two candidate face images are sorted according to the distance between the face and the verification device;

[0091] Correspondingly, the operation module includes a human identity verification unit, configured to:

[0092] Perform human identity verification on the candidate face images and the identity document information of the target verification person in sequence according to the sorting result;

[0093] If the human identity verification is successful, delete the verified candidate face images in the list of faces to be verified;

[0094] If the human identity verification fails, delete all candidate face images in the list of faces to be verified, and perform re-verification according to the updated list of faces to be verified.

[0095] Optionally, the operation module includes an update unit, configured to:

[0096] Extract a face image from the current verification scene image to obtain the current face image, and sort the current face images in ascending order according to the distance between the face and the verification device;

[0097] If it is determined that the identity verification of the target verification personnel is successful, after deleting the face image ranked first in the current face images, update the face list to be verified;

[0098] If it is determined that the identity verification of the target verification personnel fails, update the face list to be verified according to whether the face image ranked first in the current face images meets the verification standard, and perform identity verification on the target verification personnel according to the updated face list to be verified.

[0099] Optionally, after the image recognition module, there is also an operation unit for:

[0100] If not, collect the current verification scene image, extract the face image from the current verification scene image to obtain the current face image;

[0101] Sort the current face images in ascending order according to the distance between the face and the verification device;

[0102] Update the face list to be verified according to whether the face image ranked first in the current face images meets the verification standard, and perform identity verification on the target verification personnel according to the updated face list to be verified.

[0103] Optionally, the update unit or the operation unit includes a list update unit for:

[0104] If it meets the verification standard, store the current face image in the face list to be verified according to the distance between the face and the verification device, and verify the target verification personnel according to the updated face list to be verified;

[0105] If it does not meet the verification standard, re-collect the current verification scene image until it is determined that the face image ranked first meets the verification standard, and update the face list to be verified according to all the collected current verification scene images.

[0106] Optionally, the list update unit includes a first list update unit for:

[0107] After each collection of the current verification scene image, compare the face images ranked non-first in the current face images with the candidate face images in the face list to be verified. If there is a face image with a similarity greater than the preset threshold, select the face image with the maximum image quality score among the face images with a similarity greater than the preset threshold, and store it in the face list to be verified according to the distance between the face and the verification device;

[0108] After collecting the face image ranked first that meets the verification standard, store the face image ranked first in the face list to be verified.

[0109] Optionally, the list update unit includes a second list update unit for:

[0110] Compare the face images ranked non-first in the current face image with the candidate face images in the face list to be verified. If there is a face image with a similarity greater than a preset threshold, screen the face images with a similarity greater than the preset threshold according to the image quality score, and select the face image with the maximum image quality score among them;

[0111] Store the screened current face images in the face list to be verified according to the distance between the face and the verification device.

[0112] The identity verification device provided by the embodiments of the present invention can execute the identity verification method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0113] In the technical solution of this application, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations of national laws and regulations and do not violate public order and good customs.

[0114] Embodiment 5

[0115] According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0116] Figure 5 It is a schematic structural diagram of an electronic device for implementing the identity verification method of the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0117] Such as Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0118] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0119] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method of identity verification.

[0120] In some embodiments, the method of identity verification can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method of identity verification described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method of identity verification in any other appropriate manner (e.g., by means of firmware).

[0121] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0122] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0123] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0124] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0125] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0126] The computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0127] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0128] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for verifying human identities, characterized in that, Including: After collecting the ID information of the target verification person, it is determined whether there is a candidate face image in the list of faces to be verified; wherein, the candidate face image is obtained from the verification scene image when the historical verification person before the target verification person is verified; the candidate face image is at least one face image existing in the list of faces to be verified; the historical verification person is a person who has completed the identity verification on the identity verification device, and the target verification person is the person currently being verified on the identity verification device; there are no two or more face images in the list of faces to be verified with a similarity greater than a preset threshold. If it exists, identity verification is performed based on the candidate face image and the ID information of the target verification person, and the current verification scene image is collected to update the list of faces to be verified. Among them, the list of faces to be verified includes at least two candidate face images, and the at least two candidate face images are sorted according to the distance between the face and the verification device. Correspondingly, performing identity verification based on the candidate face image and the ID information of the target verification person includes: Performing identity verification on the candidate face image and the ID information of the target verification person in sequence according to the sorting result. If the identity verification is successful, the verified candidate face image in the list of faces to be verified is deleted. If the identity verification fails, all candidate face images in the list of faces to be verified are deleted, and re-verification is performed according to the updated list of faces to be verified. Among them, collecting the current verification scene image to update the list of faces to be verified includes: Extracting the face image from the current verification scene image to obtain the current face image, and sorting the current face images in ascending order according to the distance between the face and the verification device. If it is determined that the identity verification of the target verification person is successful, after deleting the face image ranked first in the current face images, the list of faces to be verified is updated. If it is determined that the identity verification of the target verification person fails, the list of faces to be verified is updated according to whether the face image ranked first in the current face images meets the verification standard, and the target verification person is verified according to the updated list of faces to be verified.

2. The method according to claim 1, characterized in that, After determining whether there is a candidate face image in the list of faces to be verified, the method further includes: If not, collect the current verification scene image, extract the face image from the current verification scene image to obtain the current face image. Sort the current face images in ascending order according to the distance between the face and the verification device. The list of faces to be verified is updated according to whether the face image ranked first in the current face images meets the verification standard, and the target verification person is verified according to the updated list of faces to be verified.

3. The method according to claim 1 or 2, characterized in that, Updating the list of faces to be verified according to whether the face image ranked first in the current face images meets the verification standard includes: If the verification standard is met, the current face image is stored in the face list to be verified according to the distance between the face and the verification device, and the target verification personnel are verified according to the updated face list to be verified; If the verification standard is not met, the current verification scene image is collected again until it is determined that the face image ranked first meets the verification standard, and the face list to be verified is updated according to all the collected current verification scene images.

4. The method according to claim 3, characterized in that Updating the face list to be verified according to all the collected current verification scene images includes: After each current verification scene image is collected, the face images ranked non-first in the current face image are compared with the candidate face images in the face list to be verified for similarity. If there are face images with similarity greater than the preset threshold, the face image with the maximum image quality score among the face images with similarity greater than the preset threshold is selected and stored in the face list to be verified according to the distance between the face and the verification device; After the face image ranked first that meets the verification standard is collected, the face image ranked first is stored in the face list to be verified.

5. The method according to claim 1, characterized in that, After deleting the face image ranked first in the current face image, the face list to be verified is updated, including: The face images ranked non-first in the current face image are compared with the candidate face images in the face list to be verified for similarity. If there are face images with similarity greater than the preset threshold, the face images with similarity greater than the preset threshold are screened according to the image quality score, and the face image with the maximum image quality score is selected; The screened current face images are stored in the face list to be verified according to the distance between the face and the verification device.

6. A human identity verification device, characterized in that, Including: An image recognition module, after collecting the ID information of the target verification personnel, determines whether there are candidate face images in the face list to be verified; wherein, the candidate face images are obtained from the verification scene images during the verification of historical verification personnel before the target verification personnel are verified; the candidate face images are at least one face image existing in the face list to be verified; historical verification personnel are those who have completed the identity verification on the identity verification device, and the target verification personnel are the current personnel being verified on the identity verification device; there are no two or more face images with similarity greater than the preset threshold in the face list to be verified; An operation module, if any, performs identity verification based on the candidate face images and the ID information of the target verification personnel, and at the same time collects the current verification scene image to update the face list to be verified; Among them, the face list to be verified includes at least two candidate face images, and the at least two candidate face images are sorted according to the distance between the face and the verification device; Correspondingly, the operation module includes an identity verification unit for: Performing identity verification on the candidate face images and the ID information of the target verification personnel in sequence according to the sorting result; If the identity verification is successful, the verified candidate face images in the face list to be verified are deleted; If the human identity verification fails, all candidate face images in the face list to be verified are deleted, and re-verification is performed based on the updated face list to be verified; Among them, the operation module includes an update unit for: extracting face images from the current verification scene image to obtain current face images, and sorting the current face images in ascending order according to the distance between the face and the verification device; if it is determined that the human identity verification of the target verification person is successful, after deleting the face image ranked first in the current face images, the face list to be verified is updated; if it is determined that the human identity verification of the target verification person fails, the face list to be verified is updated according to whether the face image ranked first in the current face images meets the verification standard, and the human identity verification of the target verification person is performed according to the updated face list to be verified.

7. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the human identity verification method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to implement the human identity verification method according to any one of claims 1-5 when executed.

Images